© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26535
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    600
    +0.11
    0.5%
    614
    +0.10
    0.5%
    287
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    287
    +0.10
    0.02
    735
    +0.10
    0.01
    Negative Logits
    etheless
    -0.71
    yip
    -0.69
    姫
    -0.67
     Nadu
    -0.67
    ashtra
    -0.64
    gencies
    -0.64
    vity
    -0.63
    oteric
    -0.62
    ueless
    -0.61
    netflix
    -0.61
    POSITIVE LOGITS
    eston
    0.75
    ¶æ
    0.74
    ħĭ
    0.71
     Wilhelm
    0.65
    º
    0.64
    Neill
    0.63
    Ľ
    0.63
     Curve
    0.63
    ij士
    0.63
    Publisher
    0.63
    Activations Density 0.030%

    No Known Activations